security-training

Build AI-powered security tools. 50+ hands-on labs covering ML, LLMs, RAG, threat detection, DFIR, and red teaming. Includes Colab notebooks, Docker environment, and CTF challenges.

Open-source cybersecurity training instruments designed for hands-on technical analysis, vulnerability identification, and skill verification.

Intentionally vulnerable Python / Flask application, built for educational purposes.

Open-source prompt injection attack console. Test AI security by firing categorized attacks at any endpoint.

This live course, “AI Attack Surface: The 10 Most Critical Threats to ML and AI Systems”, offers practical, step-by-step guidance to identify, analyze, and mitigate AI-specific attack vectors.

Provides containerized ethical hacking labs using Docker and Docker Compose for hands-on cybersecurity training, penetration testing, and vulnerability assessment practice.

Open-source, AI-powered cybersecurity war-gaming & tabletop-exercise platform. Generate realistic org scenarios, run AI game-master incident simulations, and produce after-action reports. FastAPI + Streamlit, MITRE ATT&CK-aware, Postgres-backed.

A repository of Security Engineering exercises: these exercises are designed to prepare you for interviews.

Hands-on secure code review training: learn to find vulnerabilities in Flask, Django, FastAPI through production-quality examples. Whitebox pentesting for modern web frameworks.

A 90-day, hands-on curriculum for cyber investigation: OSINT, threat intelligence, digital forensics, and fraud investigation, plus AI agent skills that run the same procedures.

Interactive game teaching phishing detection with realistic examples, immediate feedback, and infinite practice scenarios for security awareness training

A collection of containerized security vulnerabilities including privilege escalation CVEs and SUID exploits for hands-on penetration testing practice.

Intentionally vulnerable AI security training lab for LLM agents — demonstrates OWASP LLM Top 10 2025: RAG injection, tool abuse, memory poisoning, supply chain compromise, data exfiltration and more.

🔵 Blue team training environment: a complete, security-hardened Flask marketplace published with its own security audit, 278 tests, and the mistakes left visible on purpose.

Hands-on web security lab: each vulnerability shown as an exploitable /vuln route and a fixed /secure route, with tests proving both. Covers SQLi, XSS, IDOR.

An AI security agent that really attacks: local audits + red-vs-blue drills in an isolated Docker range. 100% local, MIT. 一个会自己动手攻击的 AI 安全智能体：本机隐私/漏洞体检评分 + ReAct 智能体逐步带你处置 + 真实红蓝对抗演练场（Docker 隔离网内 Kali 攻击机 × WAF × 靶机，SQL注入真实报文）。全程本地运行，不出网，MIT 开源。

Defender-side cyber incident simulator. An abstract state machine, not real infrastructure, and reinforcement-learning policies, not LLM agents. Host status is hidden behind noisy alerts, the attacker improvises, and a web console lets you play the same scenario by hand and compare your score to a trained agent's.

Modern Cybersecurity Learning and Security Analysis Platform.

Gamified, self-hosted ICS/OT security training range.

🚩 Dynamic CTF platform with isolated container-per-user-per-challenge. Auto flag rotation, scoreboard, write-up engine.